Mar 12, 2026
Economic evaluation of an AI-supported nurse self-scheduling intervention as a leadership strategy: Study protocol for a non-randomized hospital pilot
This protocol is a draft, published without a DOI.
- Aleix Fontanals-Jimenez1
- 1Universitat de Lleida
Protocol Citation: Aleix Fontanals-Jimenez 2026. Economic evaluation of an AI-supported nurse self-scheduling intervention as a leadership strategy: Study protocol for a non-randomized hospital pilot. protocols.io https://protocols.io/view/economic-evaluation-of-an-ai-supported-nurse-self-jvyvcn7w7
License: This is an open access protocol distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited
Protocol status: In development
We are still developing and optimizing this protocol
Created: March 11, 2026
Last Modified: March 12, 2026
Protocol Integer ID: 313077
Keywords: Nursing Leadership, AI-tools, Self-schedule, Nurse Management, Economic Evaluation, Healthcare Organizations, administrative burden for nurse leader, nurse leader, scheduling intervention, supported nurse self, nurse self, ai interaction in workforce management, economic evaluation of an ai, nursing competency, related nursing competency, scheduling efficiency, ai, ai interaction, improved scheduling efficiency, efficient use of human resource, leadership strategy, workforce management, collaborative human, safer staffing pattern, pilot, human resource, enhanced professional satisfaction
Abstract
The pilot is expected to demonstrate improved scheduling efficiency, more efficient use of human resources, reduced administrative burden for nurse leaders, enhanced professional satisfaction, and safer staffing patterns. The intervention is also designed to foster AI-related nursing competencies like collaborative human–AI interaction in workforce management.
Guidelines
This protocol will follow TREND (Transparent Reporting of Evaluations with Nonrandomized Designs) Guidelines for the Design and Reporting of the Implementation
Materials
1. Aldextra AI - Plano WFM (Self-Schedule AI-supported tool, adapted to Hospitalization Planning)
2. Forms (Institutional Version for Questionnaires administration in the Universitat de Lleida)
3. STATA/SE v.18.0
Troubleshooting
AI-Supported Tool Implementation
Introduce the nursing workforce of the included departments for the pilot study contract details, meaning % dedication, pre-defined schedule, accumulated hours by the professional or hours in debt to the organization.
Training Phase for the super-user (Tool Nurse Supervisor Designed, and Researchers) and for the employees, including Mobile and PC access demonstration
Data pre-intervention Collection
Phase 1
Starting Self-Schedule with AI-support in the ICU unit and Mental Health Hospitalization Unit
Technical and Clinical Supervision
Follow-Up Meetings and Data Collection
Phase II
Minor performance Adjustments
First Piloting Data Collection and Analyse (3rd month)
Phase III
Follow-up
Second Piloting Data Collection and Analyse (6th month)
INSTRUMENTS
A. Short-term (1-3 months)
Organizational
Shift coverage without incidents: % of shifts covered without emergency substitutions. Expected Objective at 3 Months: ≥97–98% of shifts covered.
Planning time: Weekly supervision hours dedicated to shift management. Expected Objective at 3 Months: ↓ ≥20% from baseline.
Administrative incidents: Number of last-minute changes / scheduling errors. Expected Objective at 3 Months: ↓ ≥10%.
Patient
Satisfaction with care: PREMs surveys (if available in the unit). Expected Objective at 3 Months: No decrease; positive trend in continuity or perceived care items.
Medication errors: Medication error reporting and adverse event recording. Expected Objective at 3 Months: ↓ ≥5%.
Professionals
Job satisfaction: JSS or MSQ survey before and after intervention. Expected Objective at 3 Months: ↑ positive perception in ≥10% of participants; improvement in flexibility and work-life balance items.
Participation and model acceptance: % of professionals using the self-management system. Expected Objective at 3 Months: ≥80% active participation at 8 weeks.
Short-term absences or sick leave: Days/hours of absence per worker (HR). Expected Objective at 3 Months: Trend to ↓ (initial reduction ≥5%).
Work stress / burnout: Short MBI or PSS scale (pre and post). Expected Objective at 3 Months: Improvement in ≥10% on emotional exhaustion scale.
Mental workload: NASA-Task Load Index (TLX). Expected Objective at 3 Months: Improvement in ≥5% on emotional exhaustion scale.
B. Long-term (6-12 months)
Organizational
Operational efficiency: Cost per service or patient served (€ per unit). Expected Objective: ↓ ≥10%.
Care continuity: Nurse-to-patient ratio per unit. Expected Objective: Maintenance or improvement.
Patient
Health outcomes (PROMs): Quality of life scales (e.g., EQ-5D, SF-12) or others according to area. Expected Objective: Maintenance or significant improvement.
Professionals
Staff retention: % of staff continuing throughout the year. Expected Objective: ↑ ≥10% from previous period.
Professional advancement / leadership: Number of positions or leadership functions held by identified nurses. Expected Objective: Progressive annual ↑.
Work climate / commitment: Climate surveys (e.g., UWES – Work Engagement Scale). Expected Objective: ↑ ≥10%.
Systemic
Model sustainability: Cost analysis vs. accumulated savings and evolution of staff indicators. Expected Objective: Net savings ≥0 (cost-neutral or positive model).
C. Cost Measurement
Cost Type
Specific Examples
Sources / Types of Analyses
Direct healthcare costs
HR personnel, training, scheduling tools or software
Center's annual accounting
Transition costs (implementation)
Meetings, coordination hours, project leadership, initial design and training
Internal project records
Potential savings and indirect costs
Reduction in sick leave, lower turnover, reduced supervision hours, overtime savings, patient outcomes (hospital stay, adverse events,...) and emergency hiring
Economic evaluation: pre/post analysis (12 months) and projection
Protocol references
1. Irvin, S. A., & Brown, H. N. (1999). Self-scheduling with Microsoft Excel. Nursing economic$, 17(4), 201–206.
2. Gray, S., Morris, M., & Bowie, D. (2023). The power of self-scheduling: Frontline nurses’ insights and perspectives to achieve staffing flexibility. Nurse Leader, 22(4). https://doi.org/10.1016/j.mnl.2023.11.012
3. Wynendaele, H., Gemmel, P., Pattyn, E., Myny, D., & Trybou, J. (2021). Systematic review: What is the impact of self-scheduling on the patient, nurse and organization?. Journal of advanced nursing, 77(1), 47–82. https://doi.org/10.1111/jan.14579
4. Fuentes, R. (2019). Implementing a Self-Scheduling Model to Decrease Nurse Turnover in Medical-Surgical Nursing. Walden Dissertations and Doctoral Studies. https://scholarworks.waldenu.edu/dissertations/7541/
5. Wynendaele, H., Gemmel, P., Peeters, E., Myny, D., & Trybou, J. (2021). The effect of self-scheduling on organizational justice and work attitudes through leader-member exchange: A cross-sectional study using propensity scores. International journal of nursing studies, 122, 104032. https://doi.org/10.1016/j.ijnurstu.2021.104032
6. Halket, D. (2016). A rapid evidence assessment : the perceptions of automated self-scheduling by acute care nurses [G]. doi:http://dx.doi.org/10.14288/1.0340631
7. Rönnberg, E., & Larsson, T. (2010). Automating the self-scheduling process of nurses in Swedish healthcare: a pilot study. Health care management science, 13(1), 35–53. https://doi.org/10.1007/s10729-009-9107-x
8. Kullberg, A., Bergenmar, M., & Sharp, L. (2016). Changed nursing scheduling for improved safety culture and working conditions - patients' and nurses' perspectives. Journal of nursing management, 24(4), 524–532. https://doi.org/10.1111/jonm.12352
9. Bailyn, L., Collins, R., & Song, Y. (2007). Self-scheduling for hospital nurses: an attempt and its difficulties. Journal of nursing management, 15(1), 72–77. https://doi.org/10.1111/j.1365-2934.2006.00633.x
10. Chang, S. J., Lee, Y. W., & Chou, W. J. (2025). Hu li za zhi The journal of nursing, 72(5), 12–18. https://doi.org/10.6224/JN.202510_72(5).03
11. Valentine, N. M., Nash, J., Hughes, D., & Douglas, K. (2008). Achieving effective staffing through a shared decision-making approach to open-shift management. The Journal of nursing administration, 38(7-8), 331–335. https://doi.org/10.1097/01.NNA.0000323941.04888.ed
12. Koning, C. (2014). Does self-scheduling increase nurses’ job satisfaction? An integrative literature review. Nursing Management, 21(6).
13. Gravenor S. (2024). Staff Self-Scheduling: Boosting Retention and Satisfaction. America’s Essential Hospitals.https://essentialhospitals.org/staff-self-scheduling-boosting-retention-and-satisfaction/
14. Epstein, M., Arakelian, E., Tucker, P., & Dahlgren, A. (2023). Managing Sustainable Working Hours within Participatory Working Time Scheduling for Nurses and Assistant Nurses: A Qualitative Interview Study with Managers and Staffing Assistants. Journal of nursing management, 2023, 8096034. https://doi.org/10.1155/2023/8096034
15. Woodcock E. (2022). Barriers and Facilitators to Automated Self-Scheduling: Consensus from a Delphi Panel of Key Stakeholders. Perspectives in health information managemen, 19(1), 1m.
16. Gebreheat, G., Teame, H., & Costa, E. I. (2023). The Impact of Transformational Leadership Style on Nurses' Job Satisfaction: An Integrative Review. SAGE open nursing, 9, 23779608231197428. https://doi.org/10.1177/23779608231197428
17. Porter-O'Grady T. (2003). Researching shared governance: a futility of focus. The Journal of nursing administration, 33(4), 251–252. https://doi.org/10.1097/00005110-200304000-00011
18. Kutney-Lee, A., Germack, H., Hatfield, L., Kelly, S., Maguire, P., Dierkes, A., Del Guidice, M., & Aiken, L. H. (2016). Nurse Engagement in Shared Governance and Patient and Nurse Outcomes. The Journal of nursing administration, 46(11), 605–612. https://doi.org/10.1097/NNA.0000000000000412
19. Fontanals-Jimenez, A., Trapero-Bertran, M., Insa-Calderón, E. (2025) Nurse-Led Interventions, Initiatives and Programs in Healthcare: A Systematic Review of their Efficacy, Efficiency, and Effectiveness.. PROSPERO CRD420251003780. Available from https://www.crd.york.ac.uk/PROSPERO/view/CRD420251003780.
20. Rizany, I., Handiyani, H., Pujasari, H., Erwandi, D., & Wulandari, C. I. (2024). Self-scheduling for nurse: A concept analysis. Multidisciplinary Reviews, 8(1), 2025021. https://doi.org/10.31893/multirev.2025021
21. Wright, C., McCartt, P., Raines, D., & Oermann, M. H. (2017). Implementation and Evaluation of Self-Scheduling in a Hospital System. Journal for nurses in professional development, 33(1), 19–24. https://doi.org/10.1097/NND.0000000000000324
22. Uhde, A., Laschke, M., & Hassenzahl, M. (2021). Design and Appropriation of Computer-supported Self-scheduling Practices in Healthcare Shift Work. Proceedings of the ACM on Human-Computer Interaction, 5(CSCW1), 1–26. https://doi.org/10.1145/3449219
23. Renggli, F. J., Gerlach, M., Bieri, J. S., Golz, C., & Sariyar, M. (2025). Integrating Nurse Preferences Into AI-Based Scheduling Systems: Qualitative Study. JMIR formative research, 9, e67747. https://doi.org/10.2196/67747
24. Inquira Health. (2025). AI-Powered Scheduling Transforming European Hospitals. https://www.inquira.health/en/blog/5-ways-ai-powered-scheduling-is-transforming-hospital-administration
25. Crónica Libre. (2024). La ‘uberización’ de la enfermería llega a España. https://www.cronicalibre.com/portada/apps-enfermeria-llegan-a-espana/
Acknowledgements
We would like to thank the Hospital Universitari Santa Maria and Aldextra, the technology partner, for their involvement in the process voluntarily and altruistically, not influencing the implementation and piloting process.